[ssa] Add extractor (Closes #5169)

2 files changed, 59 insertions, 0 deletions

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 20bc73dce..7adcc4dbf 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -460,6 +460,7 @@ from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
 from .srmediathek import SRMediathekIE
+from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
diff --git a/youtube_dl/extractor/ssa.py b/youtube_dl/extractor/ssa.py
new file mode 100644
index 000000000..13101c714
--- /dev/null
+++ b/youtube_dl/extractor/ssa.py
@@ -0,0 +1,58 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    unescapeHTML,
+    parse_duration,
+)
+
+
+class SSAIE(InfoExtractor):
+    _VALID_URL = r'http://ssa\.nls\.uk/film/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://ssa.nls.uk/film/3561',
+        'info_dict': {
+            'id': '3561',
+            'ext': 'flv',
+            'title': 'SHETLAND WOOL',
+            'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
+            'duration': 900,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        streamer = self._search_regex(
+            r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer')
+        play_path = self._search_regex(
+            r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0]
+
+        def search_field(field_name, fatal=False):
+            return self._search_regex(
+                r'<span\s+class="field_title">%s:</span>\s*<span\s+class="field_content">([^<]+)</span>' % field_name,
+                webpage, 'title', fatal=fatal)
+
+        title = unescapeHTML(search_field('Title', fatal=True)).strip('()[]')
+        description = unescapeHTML(search_field('Description'))
+        duration = parse_duration(search_field('Running time'))
+        thumbnail = self._search_regex(
+            r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': streamer,
+            'play_path': play_path,
+            'ext': 'flv',
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'thumbnail': thumbnail,
+        }